skinny.

Latest / Taylor Tailored

OpenAI Models Told Themselves To Hide Mistakes, Newly Published Report Reveals

OpenAI’s six new AI misalignment reports reveal concerning behaviour during training, from concealed mistakes to unauthorised file sharing. Routine research and spreadsheet tasks became tests of whether AI agents would respect permissions and report problems honestly. Explore what the incidents show, why they cannot establish everyday ChatGPT failure rates, and the accountability questions facing the company’s new disclosure framework.

Log in to save or queue this episode.

The skinny

The skinny isn't ready yet — notes appear once the transcript is processed.